When Blair Brettmann was a sophomore at the University of Texas at Austin, her advisor told her about the National Science Foundation’s Research Experience for Undergraduates (REU) program. The summer program enables undergraduates to conduct research at top institutions across the country. Brettmann spent the summer of 2005 at Cornell working in a national nanotechnology program — a defining experience that led to her current research in molecular engineering for integrated product development. 

“I didn't know for sure if I wanted to attend grad school until after the REU experience,” Brettmann said. “Through it, I went to high-level seminars for the first time, and working in a cleanroom was super cool.” 

Her experience was so positive that the following summer, Brettmann completed a second REU at the Massachusetts Institute of Technology, where she eventually earned her Ph.D. Now an associate professor in Georgia Tech’s School of Chemical and Biomolecular Engineering and School of Materials Science and Engineering and an Institute for Matter and Systems faculty member, Brettmann is an REU mentor for the current iteration of the nanotechnology program — now taking place at Georgia Tech. 

Brettmann’s mentee this summer, Marissa Moore, is having a similarly positive experience. A rising senior in chemical engineering at the University of Missouri-Columbia (Mizzou), Moore was already familiar with Georgia Tech because her father received his chemical engineering Ph.D. from the Institute; she hopes to do the same. Her passion for research began as she grew up with her sister, who had cerebral palsy and epilepsy. 

“We spent a lot of time in hospitals trying out new devices and looking for different medications that would help her, so I knew I wanted to make a difference in this area,” she said. 

But Moore wasn’t interested in being a doctor. Instead, she wanted to develop the materials that could be a solution for someone like her sister. Her undergraduate research focuses on materials and biomaterials for medical applications, and Georgia Tech is enabling her to deep-dive into pure materials science. 

“What I'm working on at both universities is biodegradable polymers, but at Mizzou I’m developing that polymer from the ground up, and at Tech I’m using the properties of the polymer and finding how to make them,” she explained. 

Having the opportunity to work in nanotechnology through the Institute for Materials and use Georgia Tech’s famous cleanroom made this REU stand out for Moore. 

“I had never been in the cleanroom before, so that was one of the most eye-opening experiences,” she said. “It was cool to gown up and learn all of the safety precautions.” 

For Brettmann, hands-on research experiences like this make the REU program unique — and crucial — for potential graduate students. 

“Having your experiments fail, or even having things not turn out as you expect them to is an important part of the graduate research experience,” she said. “One of the best things about REU is it can be a first experience for people and help them decide what to do in grad school later on.”

CREATE-X is built to help students integrate entrepreneurship into their academic journey through courses, workshops, and a startup accelerator. This spring, a new set of students displayed their solutions to real-world problems at the I2P Showcase. It’s our privilege to shine a light on and celebrate those journeys. Today’s spotlight focuses on the spring I2P Showcase third-place winners. 

Electrosuit 

Aubrey Hall, a first-year biomedical student, and Sherya Chakraborty, a first-year computer science major, founded a startup to produce a garment that eases the use of at-home, prescribed electrical stimulation for people with chronic pain, stroke, and motor impairments.

What made you interested in building this solution?

“I did research at Northwestern for a couple of years before this, and some of the patients I worked with had severe stroke and spasticity in their arms,” Chakraborty said. “I found out that when they tried using at-home prescribed electrical stimulation, they had trouble setting it off themselves. So, we created a garment to ease pressure on that.”

What part of the course was most helpful to you?

“One of our mentors, Sun Mi Park, was the first person to patent printable wires on fabric, and that gave us some inspiration to make our garment even more compact, easier to use, and integrate some interesting ideas that we wouldn’t have been able to without our mentors. So, our mentors are honestly the best part of the program,” Chakraborty said.

“For me, you don’t get a lot of chances to apply these engineering courses outside of the classroom,” said Hall. “This course is a really interesting way to get firsthand experience building a prototype and really understand the engineering process.”

What’s so special about CREATE-X?

“I think these student projects are the future, and a lot of these projects make it out of college and become actual companies. Giving students that possibility to make a change just from a simple idea and fueling that with funding so we don’t have to take risks out of our own pockets is a, really big deal,” Chakraborty said.

“It’s helpful to have that safety net, knowing that you have your mentors to back you, and also the people of the program to back you. It brings a lot of security and opportunity to try different things out and not have to be so fearful of failure. Even if you fail a million times, you can get back up and try again,” Hall said.

What’s the best insight you’ve gained from doing this?

“I think one big misconception is that entrepreneurship has a lot to do with finance and business and just lucrative ideas, but it’s pretty important to understand that you can solve a seemingly everyday problem,” said Chakraborty. “If it affects you or your friends, it’s still worth trying to find a way to solve it, especially backed up with money and mentors from CREATE-X. What’s the harm in trying something out?” 

“Don’t try to make it feel like it’s an all-or-nothing project,” Hall said. “You’re allowed to live your life as a college student but also pursue these interesting ideas and figure out if you enjoy entrepreneurship. It shouldn’t be this daunting task where if you don’t put everything in, you’re going to fail.”

“It’s also important to keep an open mind. We might come in with an idea and a very specific way of executing that idea, but we found out through talking with mentors, and with other students and people who gave us advice, that sometimes the idea you come in with is not going to be the same thing you end up with,” Chakraborty said. 

Next Steps

“We’ve only done four or five prototypes so far,” she noted. “We want to do at least 12 of those prototypes and keep working with our mentors, keep making connections at Emory, and just constantly getting more and more feedback about our prototypes until we get to a state where we’re satisfied, and we can demo our product and work with physical therapists across Atlanta.”

If you’re a student interested in building your own product for college credit, apply for I2P. And join us for Demo Day, Aug. 29, at 5 p.m., in the Georgia Tech Exhibition Hall to see new CREATE-X founders launch products in a variety of industries. Tickets are free but limited. Register today to secure your spot.

During the school year and the summer, Georgia Tech students can incorporate entrepreneurship into their college experience through courses, workshops, special events, and even a startup accelerator. CREATE-X invites you to delve into the journeys of our top achievers, this time focusing on the Spring 2024 I2P Showcase first-place winners: 

Dolfin Solutions

Marianna Cao, James Gao, and Jaeheon Shim, first-year computer science majors, are the founders of Dolfin Solutions, a personal financial management platform that promises a unified solution to budgeting, transaction management, and expense tracking, among other personal finance tasks. 

What challenges did you have in I2P, and how did you work through them?

 “We were really lucky to get an excellent mentor, Aaron Hillegass. He has a lot of experience in the industry as a startup founder himself, and he gave us a lot of help, both technical as well as business, throughout the process. That helped us make better decisions,” Gao said.

“I think the biggest challenge was, I had done projects in the past by myself, writing the full stack, but working together, communicating the requirements, and integrating everyone's different code at the end was a little bit of a logistical struggle,” Shim said. “But we managed to figure it out.”

What advice do you have for students interested in I2P or entrepreneurship in general?

“Go for it. It's a three-credit course, so it counts toward your junior capstone as well. You get $500. Now is the perfect time to start because you don't have much to lose. If you're doing I2P and your company fails, you still have four years of college; you can still pursue a traditional path. It's a little risk but a lot to gain,” Shim said.

“Even if you pivot or change your idea, it's important to believe in what you started,” said Cao. “If you don't believe in your app, then nobody else does. Right now, you have all of the friends, mentors, professors, and the right resources, and money is not an issue. It's a good opportunity for you to work on it on the side, and maybe it could turn into something.”

What’s Next?

“We’re going to build for the iOS and Android platforms, and then we're going to deploy hopefully by the end of summer,” Shim said. 

If you’re a student interested in building your own product for college credit, apply for I2P. And join us for Demo Day, Aug. 29, at 5 p.m., in the Georgia Tech Exhibition Hall to see new CREATE-X founders launch products in a variety of industries. Tickets are free but limited. Register today to secure your spot.

Georgia Tech will lead a consortium of 12 universities and 12 national labs as part of a $25 million U.S. Department of Energy National Nuclear Security Administration (NNSA) award. This is the second time Georgia Tech has won this award and led research and development efforts to aid NNSA’s nonproliferation, nuclear science, and security endeavors.

The Consortium for Enabling Technologies and Innovation (ETI) 2.0 will leverage the strong foundation of interdisciplinary, collaboration-driven technological innovation developed in the ETI Consortium funded in 2019. The technical mission of the ETI 2.0 team is to advance technologies across three core disciplines: data science and digital technologies in nuclear security and nonproliferation, precision environmental analysis for enhanced nuclear nonproliferation vigilance and emergency response, and emerging technologies. They will be advanced by research projects in novel radiation detectors, algorithms, testbeds, and digital twins.

“What we're trying to do is bring those emergent technologies that are not implemented right now to fruition,” said Anna Erickson, Woodruff Professor and associate chair for research in the George W. Woodruff School of Mechanical Engineering, who leads both grants. “We want to understand what's ahead in the future for both the technology and the threats, which will help us determine how we can address it today.” 

While half the original collaborators remain, Erickson sought new institutional partners for their research expertise, including Abilene Christian University, University of Alaska Fairbanks, Stony Brook University, Rensselaer Polytechnic Institute, and Virginia Commonwealth University. Other university collaborators include the Colorado School of Mines, the Massachusetts Institute of Technology, Ohio State University, Texas A&M University, the University of Texas at Austin, and the University of Wisconsin–Madison.  

National lab partners are the Argonne National Laboratory, Brookhaven National Laboratory, Idaho National Laboratory, Lawrence Berkeley National Laboratory, Lawrence Livermore National Laboratory, Los Alamos National Laboratory, Nevada National Security Site, Oak Ridge National Laboratory, Pacific Northwest National Laboratory, Princeton Plasma Physics Laboratory, Sandia National Laboratories, and Savannah River National Laboratory.

The partners, along with the other NNSA Consortia, gathered at Texas A&M in June to present the new results of the research — NNSA DNN R&D University Program Review — and the kickoff will be hosted in Atlanta in February 2025. More than 300 collaborators, including 150 students, met for four days to share their research and develop new partnerships. 

Engaging students in research in the nuclear nonproliferation field is a key part of the award. The plan is to train over 50 graduate students, provide internships for graduate and undergraduate students, and offer faculty-student lab visit fellowships. This pipeline aims to develop well-rounded professionals equipped with the expertise to tackle future nonproliferation challenges.

“Because nuclear proliferation is a multifaceted problem, we try to bring together people from outside nuclear engineering to have a conversation about the problems and solutions,” Erickson said.

“One of the biggest accomplishments of ETI 1.0 is this incredible relationship that our university PIs have been able to forge with national labs,” she said. “Over five years, we've supported over 70 student internships at national labs, and we have already transitioned a number of Ph.D. students to careers at national labs.” 

As the consortium efforts continue, the team looks forward to the next phase of engagement with government, university, and national lab partners.

“With a united team and a focus on cutting-edge technologies, the ETI 2.0 consortium is poised to break new ground in nuclear nonproliferation,” Erickson said. “Collaboration is the fuel, and innovation is the engine.”

Hepatic, or liver, disease affects more than 100 million people in the U.S. About 4.5 million adults (1.8%) have been diagnosed with liver disease, but it is estimated that between 80 and 100 million adults in the U.S. have undiagnosed fatty liver disease in varying stages. Over time, undiagnosed and untreated hepatic diseases can lead to cirrhosis, a severe scarring of the liver that cannot be reversed. 

Most hepatic diseases are chronic conditions that will be present over the life of the patient, but early detection improves overall health and the ability to manage specific conditions over time. Additionally, assessing patients over time allows for effective treatments to be adjusted as necessary. The standard protocol for diagnosis, as well as follow-up tissue assessment, is a biopsy after the return of an abnormal blood test, but biopsies are time-consuming and pose risks for the patient. Several non-invasive imaging techniques have been developed to assess the stiffness of liver tissue, an indication of scarring, including magnetic resonance elastography (MRE).

MRE combines elements of ultrasound and MRI imaging to create a visual map showing gradients of stiffness throughout the liver and is increasingly used to diagnose hepatic issues. MRE exams, however, can fail for many reasons, including patient motion, patient physiology, imaging issues, and mechanical issues such as improper wave generation or propagation in the liver. Determining the success of MRE exams depends on visual inspection of technologists and radiologists. With increasing work demands and workforce shortages, providing an accurate, automated way to classify image quality will create a streamlined approach and reduce the need for repeat scans. 

Professor Jun Ueda in the George W. Woodruff School of Mechanical Engineering and robotics Ph.D. student Heriberto Nieves, working with a team from the Icahn School of Medicine at Mount Sinai, have successfully applied deep learning techniques for accurate, automated quality control image assessment. The research, “Deep Learning-Enabled Automated Quality Control for Liver MR Elastography: Initial Results,” was published in the Journal of Magnetic Resonance Imaging.

Using five deep learning training models, an accuracy of 92% was achieved by the best-performing ensemble on retrospective MRE images of patients with varied liver stiffnesses. The team also achieved a return of the analyzed data within seconds. The rapidity of image quality return allows the technician to focus on adjusting hardware or patient orientation for re-scan in a single session, rather than requiring patients to return for costly and timely re-scans due to low-quality initial images.

This new research is a step toward streamlining the review pipeline for MRE using deep learning techniques, which have remained unexplored compared to other medical imaging modalities.  The research also provides a helpful baseline for future avenues of inquiry, such as assessing the health of the spleen or kidneys. It may also be applied to automation for image quality control for monitoring non-hepatic conditions, such as breast cancer or muscular dystrophy, in which tissue stiffness is an indicator of initial health and disease progression. Ueda, Nieves, and their team hope to test these models on Siemens Healthineers magnetic resonance scanners within the next year.

Publication
Nieves-Vazquez, H.A., Ozkaya, E., Meinhold, W., Geahchan, A., Bane, O., Ueda, J. and Taouli, B. (2024), Deep Learning-Enabled Automated Quality Control for Liver MR Elastography: Initial Results. J Magn Reson Imaging. https://doi.org/10.1002/jmri.29490

Prior Work 
Robotically Precise Diagnostics and Therapeutics for Degenerative Disc Disorder

Related Material
Editorial for “Deep Learning-Enabled Automated Quality Control for Liver MR Elastography: Initial Results”

New research from Georgia Tech is giving scientists more control options over generative artificial intelligence (AI) models in their studies. Greater customization from this research can lead to discovery of new drugs, materials, and other applications tailor-made for consumers.

The Tech group dubbed its method PRODIGY (PROjected DIffusion for controlled Graph Generation). PRODIGY enables diffusion models to generate 3D images of complex structures, such as molecules from chemical formulas. 

Scientists in pharmacology, materials science, social network analysis, and other fields can use PRODIGY to simulate large-scale networks. By generating 3D molecules from multiple graph datasets, the group proved that PRODIGY could handle complex structures.

In keeping with its name, PRODIGY is the first plug-and-play machine learning (ML) approach to controllable graph generation in diffusion models. This method overcomes a known limitation inhibiting diffusion models from broad use in science and engineering.

“We hope PRODIGY enables drug designers and scientists to generate structures that meet their precise needs,” said Kartik Sharma, lead researcher on the project. “It should also inspire future innovations to precisely control modern generative models across domains.” 

PRODIGY works on diffusion models, a generative AI model for computer vision tasks. While suitable for image creation and denoising, diffusion methods are limited because they cannot accurately generate graph representations of custom parameters a user provides.

PRODIGY empowers any pre-trained diffusion model for graph generation to produce graphs that meet specific, user-given constraints. This capability means, as an example, that a drug designer could use any diffusion model to design a molecule with a specific number of atoms and bonds.

The group tested PRODIGY on two molecular and five generic datasets to generate custom 2D and 3D structures. This approach ensured the method could create such complex structures, accounting for the atoms, bonds, structures, and other properties at play in molecules. 

Molecular generation experiments with PRODIGY directly impact chemistry, biology, pharmacology, materials science, and other fields. The researchers say PRODIGY has potential in other fields using large networks and datasets, such as social sciences and telecommunications.

These features led to PRODIGY’s acceptance for presentation at the upcoming International Conference on Machine Learning (ICML 2024). ICML 2024 is the leading international academic conference on ML. The conference is taking place July 21-27 in Vienna.

Assistant Professor Srijan Kumar is Sharma’s advisor and paper co-author. They worked with Tech alumnus Rakshit Trivedi (Ph.D. CS 2020), a Massachusetts Institute of Technology postdoctoral associate.

Twenty-four Georgia Tech faculty from the Colleges of Computing and Engineering will present 40 papers at ICML 2024. Kumar is one of six faculty representing the School of Computational Science and Engineering (CSE) at the conference.

Sharma is a fourth-year Ph.D. student studying computer science. He researches ML models for structured data that are reliable and easily controlled by users. While preparing for ICML, Sharma has been interning this summer at Microsoft Research in the Research for Industry lab.

“ICML is the pioneering conference for machine learning,” said Kumar. “A strong presence at ICML from Georgia Tech illustrates the ground-breaking research conducted by our students and faculty, including those in my research group.”

Visit https://sites.gatech.edu/research/icml-2024 for news and coverage of Georgia Tech research presented at ICML 2024.

A new machine learning (ML) model created at Georgia Tech is helping neuroscientists better understand communications between brain regions. Insights from the model could lead to personalized medicine, better brain-computer interfaces, and advances in neurotechnology.

The Georgia Tech group combined two current ML methods into their hybrid model called MRM-GP (Multi-Region Markovian Gaussian Process). 

Neuroscientists who use MRM-GP learn more about communications and interactions within the brain. This in turn improves understanding of brain functions and disorders.

“Clinically, MRM-GP could enhance diagnostic tools and treatment monitoring by identifying and analyzing neural activity patterns linked to various brain disorders,” said Weihan Li, the study’s lead researcher. 

“Neuroscientists can leverage MRM-GP for its robust modeling capabilities and efficiency in handling large-scale brain data.” 

MRM-GP reveals where and how communication travels across brain regions. 

The group tested MRM-GP using spike trains and local field potential recordings, two kinds of measurements of brain activity. These tests produced representations that illustrated directional flow of communication among brain regions. 

Experiments also disentangled brainwaves, called oscillatory interactions, into organized frequency bands. MRM-GP’s hybrid configuration allows it to model frequencies and phase delays within the latent space of neural recordings.

MRM-GP combines the strengths of two existing methods: the Gaussian process (GP) and linear dynamical systems (LDS). The researchers say that MRM-GP is essentially an LDS that mirrors a GP.

LDS is a computationally efficient and cost-effective method, but it lacks the power to produce representations of the brain. GP-based approaches boost LDS's power, facilitating the discovery of variables in frequency bands and communication directions in the brain.

Converting GP outputs into an LDS is a difficult task in ML. The group overcame this challenge by instilling separability in the model’s multi-region kernel. Separability establishes a connection between the kernel and LDS while modeling communication between brain regions.

Through this approach, MRM-GP overcomes two challenges facing both neuroscience and ML fields. The model helps solve the mystery of intraregional brain communication. It does so by bridging a gap between GP and LDS, a feat not previously accomplished in ML.

“The introduction of MRM-GP provides a useful tool to model and understand complex brain region communications,” said Li, a Ph.D. student in the School of Computational Science and Engineering (CSE). 

“This marks a significant advancement in both neuroscience and machine learning.”

Fellow doctoral students Chengrui Li and Yule Wang co-authored the paper with Li. School of CSE Assistant Professor Anqi Wu advises the group. 

Each MRM-GP student pursues a different Ph.D. degree offered by the School of CSE. W. Li studies computer science, C. Li studies computational science and engineering, and Wang studies machine learning. The school also offers Ph.D. degrees in bioinformatics and bioengineering.

Wu is a 2023 recipient of the Sloan Research Fellowship for neuroscience research. Her work straddles two of the School’s five research areas: machine learning and computational bioscience. 

MRM-GP will be featured at the world’s top conference on ML and artificial intelligence. The group will share their work at the International Conference on Machine Learning (ICML 2024), which will be held July 21-27 in Vienna. 

ICML 2024 also accepted for presentation a second paper from Wu’s group intersecting neuroscience and ML. The same authors will present A Differentiable Partially Observable Generalized Linear Model with Forward-Backward Message Passing.

Twenty-four Georgia Tech faculty from the Colleges of Computing and Engineering will present 40 papers at ICML 2024. Wu is one of six faculty representing the School of CSE who will present eight total papers.

The group’s ICML 2024 presentations exemplify Georgia Tech’s focus on neuroscience research as a strategic initiative.  

Wu is an affiliated faculty member with the Neuro Next Initiative, a new interdisciplinary program at Georgia Tech that will lead research in neuroscience, neurotechnology, and society. The University System of Georgia Board of Regents recently approved a new neuroscience and neurotechnology Ph.D. program at Georgia Tech. 

“Presenting papers at international conferences like ICML is crucial for our group to gain recognition and visibility, facilitates networking with other researchers and industry professionals, and offers valuable feedback for improving our work,” Wu said. 

“It allows us to share our findings, stay updated on the latest developments in the field, and enhance our professional development and public speaking skills.”

Visit https://sites.gatech.edu/research/icml-2024 for news and coverage of Georgia Tech research presented at ICML 2024.

As the summer heat intensifies, with temperatures sometimes soaring to triple digits, the question of which fabrics are best for staying cool becomes particularly relevant. Sundaresan Jayaraman, a professor in Georgia Tech’s School of Materials Science and Engineering, offers insights into the properties of various fabrics and why some are more effective than others in hot, humid conditions.

Jayaraman, a renowned expert in fibers, polymers, and textiles, recognizes linen as the best fabric for hot and humid conditions. He explains that linen's effectiveness lies in its superior moisture management properties. The fiber structure of linen allows it to absorb moisture quickly and then transport it away from the body. This is due to linen's high moisture regain capacity, which means it can absorb a significant amount of moisture without feeling damp.

“The moisture vapor transport rate for linen is much greater than that for cotton or polyester,” he explained. Additionally, linen's bending rigidity prevents it from clinging to the body, allowing for better air circulation.

Cotton is another popular fabric for summer, known for its softness and breathability. However, Jayaraman points out that while cotton effectively absorbs moisture, it tends to retain it longer than linen, making it feel clammy in extreme heat. Cotton's moisture vapor transmission rate is lower than linen’s, meaning it doesn't dry as quickly.

The structure of cotton fibers, which are ribbon-like and can trap more water, also affects cotton’s performance. While it’s more prone to sticking to the body due to its lower bending rigidity, cotton is generally comfortable for less humid conditions or for shorter durations in the heat.

While polyester may not be the first fabric that comes to mind for summer, its performance can be significantly enhanced with chemical treatments. Dri-FIT technology, for instance, improves polyester’s moisture-wicking properties, making it a popular choice for athletic wear.

“Regular polyester is terrible when it comes to moisture absorption,” admitted Jayaraman. “But Dri-FIT polyester doesn’t feel clammy and is very comfortable for being physically active in the summer months.”

While functionality is crucial, aesthetics also play a role in fabric choice for the summer. Linen, despite its excellent cooling properties, is prone to wrinkling and may not drape as elegantly as cotton or treated polyester. Jayaraman notes that linen's natural stiffness, which contributes to its cooling benefits, also leads to its tendency to wrinkle. He says, “For a crisp appearance, linen garments often require ironing before wear.” For those prioritizing appearance, cotton offers a softer drape and a smoother look, albeit with slightly less cooling efficiency.